Creating Generator of Pseudowords and Classifying Them by Similarity with Words from Russian Language Dictionary Using Machine Learning
摘要
In this article, a pseudoword is defined as a unit of speech or text that appears to be a real word in Russian but actually has no meaning. A real or natural word is a unit of speech or text that has an interpretation and is included in a dictionary. The paper presents two models for working with the Russian language: a generator that creates pseudowords resembling real words and a classifier that evaluates the degree of similarity between the entered sequence of characters and real words. The classifier is used to evaluate the results produced by the generator. Both models are based on recurrent neural networks with long short-term memory layers and are trained on a dataset of Russian nouns. The resulting file contained a list of the generated pseudowords that were then evaluated by the classifier to filter out those that were not similar enough to real words. Pseudowords can be used in naming, branding, and layout design, in art, creative works, and in linguistic studies exploring the language structure and words.